udpate readme

This commit is contained in:
Wendong 2025-03-16 16:50:06 +08:00
parent 8e2ee20e3e
commit ea74c16873
2 changed files with 87 additions and 47 deletions

View File

@ -66,29 +66,10 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
- [🎬 Demo Video](#-demo-video)
- [✨️ Core Features](#-core-features)
- [🛠️ Installation](#-installation)
- [Option 1: Using uv (Recommended)](#option-1-using-uv-recommended)
- [Option 2: Using venv and pip](#option-2-using-venv-and-pip)
- [Option 3: Using conda](#option-3-using-conda)
- [**Setup Environment Variables**](#setup-environment-variables)
- [Option 1: Using a `.env` File (Recommended)](#option-1-using-a-env-file-recommended)
- [Option 2: Setting Environment Variables Directly](#option-2-setting-environment-variables-directly)
- [**Running with Docker**](#running-with-docker)
- [🚀 Quick Start](#-quick-start)
- [Basic Usage](#basic-usage)
- [Running with Different Models](#running-with-different-models)
- [Model Requirements](#model-requirements)
- [Supported Models](#supported-models)
- [Example Tasks](#example-tasks)
- [🧰 Toolkits and Capabilities](#-toolkits-and-capabilities)
- [Model Context Protocol (MCP)](#model-context-protocol-mcp)
- [Available Toolkits](#available-toolkits)
- [Available Toolkits](#available-toolkits-1)
- [Multimodal Toolkits (Require multimodal model capabilities)](#multimodal-toolkits-require-multimodal-model-capabilities)
- [Text-Based Toolkits](#text-based-toolkits)
- [Customizing Your Configuration](#customizing-your-configuration)
- [🌐 Web Interface](#-web-interface)
- [Starting the Web UI](#starting-the-web-ui)
- [Features](#features)
- [🧪 Experiments](#-experiments)
- [⏱️ Future Plans](#-future-plans)
- [📄 License](#-license)
@ -97,7 +78,6 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
- [🔥 Community](#-community)
- [❓ FAQ](#-faq)
- [📚 Exploring CAMEL Dependency](#-exploring-camel-dependency)
- [Accessing CAMEL Source Code](#accessing-camel-source-code)
- [⭐ Star History](#-star-history)
# 🔥 News
@ -280,6 +260,10 @@ Alternatively, you can set environment variables directly in your terminal:
## **Running with Docker**
OWL can be easily deployed using Docker, which provides a consistent environment across different platforms.
### **Setup Instructions**
```bash
# Clone the repository
git clone https://github.com/camel-ai/owl.git
@ -288,41 +272,63 @@ cd owl
# Configure environment variables
cp owl/.env_template owl/.env
# Edit the .env file and fill in your API keys
```
# Option 1: Using docker-compose directly
# Docker image options:
# Option 1: Use pre-built image from Docker Hub (default, faster)
# This option downloads a ready-to-use image and is recommended for most users
### **Deployment Options**
#### **Option 1: Using Pre-built Image (Recommended)**
```bash
# This option downloads a ready-to-use image from Docker Hub
# Fastest and recommended for most users
docker-compose up -d
# Option 2: Build image locally (more customizable)
# If you need to customize the Docker image or are unable to access Docker Hub:
# Run OWL inside the container
docker-compose exec owl bash
cd .. && source .venv/bin/activate
playwright install-deps
xvfb-python examples/run.py
```
#### **Option 2: Building Image Locally**
```bash
# For users who need to customize the Docker image or cannot access Docker Hub:
# 1. Open docker-compose.yml
# 2. Comment out the "image: mugglejinx/owl:latest" line
# 3. Uncomment the "build:" section and its nested properties
# 4. Then run:
docker-compose up -d --build
cd .container
# Run OWL inside the container
docker-compose exec owl bash
# activate the virtual environment
cd .. && source .venv/bin/activate
playwright install-deps
#run example demo script
playwright install-deps
xvfb-python examples/run.py
```
# Option 3: Build and run using the provided scripts
#### **Option 3: Using Convenience Scripts**
```bash
# Navigate to container directory
cd .container
# Make the script executable and build the Docker image
chmod +x build_docker.sh
./build_docker.sh
# Run OWL inside the container
# Run OWL with your question
./run_in_docker.sh "your question"
```
### **MCP Desktop Commander Setup**
If using MCP Desktop Commander within Docker, run:
```bash
npx -y @wonderwhy-er/desktop-commander setup --force-file-protocol
```
For more detailed Docker usage instructions, including cross-platform support, optimized configurations, and troubleshooting, please refer to [DOCKER_README.md](.container/DOCKER_README_en.md).
# 🚀 Quick Start

View File

@ -253,7 +253,9 @@ OWL 需要各种 API 密钥来与不同的服务进行交互。`owl/.env_templat
## **使用Docker运行**
如果您希望使用Docker运行OWL项目我们提供了完整的Docker支持
OWL可以通过Docker轻松部署Docker提供了跨不同平台的一致环境。
### **设置说明**
```bash
# 克隆仓库
@ -263,32 +265,64 @@ cd owl
# 配置环境变量
cp owl/.env_template owl/.env
# 编辑.env文件填入您的API密钥
```
# 选项1直接使用docker-compose
cd .container
### **部署选项**
#### **选项1使用预构建镜像推荐**
```bash
# 此选项从Docker Hub下载一个即用型镜像
# 最快速且推荐给大多数用户
docker-compose up -d
# 在容器中运行OWL
docker-compose exec owl bash
# 激活虚拟环境
cd .. && source .venv/bin/activate
playwright install-deps
#运行例子演示脚本
playwright install-deps
xvfb-python examples/run.py
```
# 选项2使用提供的脚本构建和运行
#### **选项2本地构建镜像**
```bash
# 适用于需要自定义Docker镜像或无法访问Docker Hub的用户
# 1. 打开docker-compose.yml
# 2. 注释掉"image: mugglejinx/owl:latest"行
# 3. 取消注释"build:"部分及其嵌套属性
# 4. 然后运行:
docker-compose up -d --build
# 在容器中运行OWL
docker-compose exec owl bash
cd .. && source .venv/bin/activate
playwright install-deps
xvfb-python examples/run.py
```
#### **选项3使用便捷脚本**
```bash
# 导航到容器目录
cd .container
# 使脚本可执行并构建Docker镜像
chmod +x build_docker.sh
./build_docker.sh
# 在容器中运行OWL
# 使用您的问题运行OWL
./run_in_docker.sh "您的问题"
```
更多详细的Docker使用说明包括跨平台支持、优化配置和故障排除请参阅 [DOCKER_README.md](.container/DOCKER_README.md)
### **MCP Desktop Commander设置**
如果在Docker中使用MCP Desktop Commander请运行
```bash
npx -y @wonderwhy-er/desktop-commander setup --force-file-protocol
```
更多详细的Docker使用说明包括跨平台支持、优化配置和故障排除请参阅 [DOCKER_README.md](.container/DOCKER_README_en.md)
# 🚀 快速开始